paper-with-me

Papers

GaussianSSC: Triplane-Guided Directional Gaussian Fields for 3D Semantic Completion

2026-03-23 · Ruiqi Xian, Jing Liang, He Yin, Xuewei Qi, Dinesh Manocha arxiv

We present \emph{GaussianSSC}, a two-stage, grid-native and triplane-guided approach to semantic scene completion (SSC) that injects the benefits of Gaussians without replacing the voxel grid or maintaining a separate Gaussian set. We introduce \emph{Gaussian Anchoring}, a sub-pixel, Gaussian-weighted image aggregation over fused FPN features that tightens voxel--image alignment and improves monocular occupancy estimation. We further convert point-like voxel features into a learned per-voxel Gaussian field and refine triplane features via a triplane-aligned \emph{Gaussian--Triplane Refinement} module that combines \emph{local gathering} (target-centric) and \emph{global aggregation} (source-centric). This directional, anisotropic support captures surface tangency, scale, and occlusion-aware asymmetry while preserving the efficiency of triplane representations. On SemanticKITTI~\cite{behley2019semantickitti}, GaussianSSC improves Stage~1 occupancy by +1.0\% Recall, +2.0\% Precision, and +1.8\% IoU over state-of-the-art baselines, and improves Stage~2 semantic prediction by +1.8\% IoU and +0.8\% mIoU.

📄 PDF Abstract BibTeX arXiv:2603.21487

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Disentangled Generation and Aggregation for Robust Radiance Fields

2024-09-24 · Shihe Shen, Huachen Gao, Wangze Xu, Rui Peng 외

The utilization of the triplane-based radiance fields has gained attention in recent years due to its ability to effectively disentangle 3D scenes with a high-quality representation and low computation cost. A key requir…

NeRFNovel View Synthesis

BrightDreamer: Generic 3D Gaussian Generative Framework for Fast Text-to-3D Synthesis

2024-03-17 · Lutao Jiang, Xu Zheng, Yuanhuiyi Lyu, Jiazhou Zhou 외

Text-to-3D synthesis has recently seen intriguing advances by combining the text-to-image priors with 3D representation methods, e.g., 3D Gaussian Splatting (3D GS), via Score Distillation Sampling (SDS). However, a hurd…

3D GenerationText to 3D

Representing 3D Shapes With 64 Latent Vectors for 3D Diffusion Models

2025-03-11 · In Cho, Youngbeom Yoo, Subin Jeon, Seon Joo Kim

Constructing a compressed latent space through a variational autoencoder (VAE) is the key for efficient 3D diffusion models. This paper introduces COD-VAE, a VAE that encodes 3D shapes into a COmpact set of 1D latent vec…

Decoder

DT-NeRF: Decomposed Triplane-Hash Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis

2023-09-14 · Yaoyu Su, Shaohui Wang, Haoqian Wang

In this paper, we present the decomposed triplane-hash neural radiance fields (DT-NeRF), a framework that significantly improves the photorealistic rendering of talking faces and achieves state-of-the-art results on key …

NeRF

3D Neural Field Generation using Triplane Diffusion

2022-11-30 · CVPR 2023 1 · J. Ryan Shue, Eric Ryan Chan, Ryan Po, Zachary Ankner 외

Diffusion models have emerged as the state-of-the-art for image generation, among other tasks. Here, we present an efficient diffusion-based model for 3D-aware generation of neural fields. Our approach pre-processes trai…

3D GenerationDiversityImage Generation